An Analysis of Variance of Nominal Data

This paper considers a common problem in analysis of variance where the responses to a set of treatments are nominal (i.e. are recorded in frequencies) with no underlying metric. Reasoning by analogy from standard analysis of variance of a two-way classification we develop chi-square tests for significance of treatments and interactions. Two tests are proposed for interaction and their asymptotic properties are studied.     

Topographic Factor Analysis: A Bayesian Model for Inferring Brain Networks from Neural Data

The neural patterns recorded during a neuroscientific experiment reflect complex interactions between many brain regions, each comprising millions of neurons. However, the measurements themselves are typically abstracted from that underlying structure. For example, functional magnetic resonance imaging (fMRI) datasets comprise a time series of three-dimensional images, where each voxel in an image (roughly) reflects the activity of the brain structure(s)–located at the corresponding point in space–at the time the image was collected. FMRI data often exhibit strong spatial correlations, whereby nearby voxels behave similarly over time as the underlying brain structure modulates its activity. Here we develop topographic factor analysis (TFA), a technique that exploits spatial correlations in fMRI data to recover the underlying structure that the images reflect. Specifically, TFA casts each brain image as a weighted sum of spatial functions. The parameters of those spatial functions, which may be learned by applying TFA to an fMRI dataset, reveal the locations and sizes of the brain structures activated while the data were collected, as well as the interactions between those structures.     

Risky Business: Factor Analysis of Survey Data – Assessing the Probability of Incorrect Dimensionalisation

This paper undertakes a systematic assessment of the extent to which factor analysis the correct number of latent dimensions (factors) when applied to ordered-categorical survey items (so-called Likert items). We simulate 2400 data sets of uni-dimensional Likert items that vary systematically over a range of conditions such as the underlying population distribution, the number of items, the level of random error, and characteristics of items and item-sets. Each of these datasets is factor analysed in a variety of ways that are frequently used in the extant literature, or that are recommended in current methodological texts. These include exploratory factor retention heuristics such as Kaiser’s criterion, Parallel Analysis and a non-graphical scree test, and (for exploratory and confirmatory analyses) evaluations of model fit. These analyses are conducted on the basis of Pearson and polychoric correlations. We find that, irrespective of the particular mode of analysis, factor analysis applied to ordered-categorical survey data very often leads to over-dimensionalisation. The magnitude of this risk depends on the specific way in which factor analysis is conducted, the number of items, the properties of the set of items, and the underlying population distribution. The paper concludes with a discussion of the consequences of over-dimensionalisation, and a brief mention of alternative modes of analysis that are much less prone to such problems.     

A Selected And Annotated Bibliography On Wild Rice

Abstract

Information germane to a compre hensive anthropological study of wild rice and its use as a subsistence item is contained in the literature of several disciplines. The following annota.ted bibliography attempts to provide an indication of the location and nature of some of this material.     

A General Computing Algorithm for Factor Analysis

A general algorithm for the factor analysis is developed, which contains the alpha factor analysis, the maximum likelihood method and the minres method as special cases. This algorithm, which is a multidimensional NEWTON algorithm, uses the partial derivatives of the reproduced communalities with respect to the inserted ones. The partial derivatives are got by means of the perturbation theory.     

Stoichiometry-driven Protein Folding: A Comment

Abstract

We have found, with the aid of 2-D gel electrophoresis, that double-stranded human telomeric repeat, (T₂AG₃)₁₂·(C₃TA₂)₁₂, being cloned within a plasmid, forms a protonated superhelically-induced structure. Experiments on chemical and enzymatic probing also indicate that the human telomeric repeats adopt an unusual structure. We have proposed an eclectic model for this structure in which four different elements coexist: a non-orthodox intramolecular triplex stabilized by the canonical protonated C · G*C⁺ base-triads and highly enriched by non-canonical base-triads; the intramolecular quadruplex formed by a portion of the G-rich strand; the single-stranded region encompassing a portion of the G-rich strand and, probably, the (C,A)-hairpin formed by a portion of the C-rich strand.     

MultiElec: A MATLAB Based Application for MEA Data Analysis

We present MultiElec, an open source MATLAB based application for data analysis of microelectrode array (MEA) recordings. MultiElec displays an extremely user-friendly graphic user interface (GUI) that allows the simultaneous display and analysis of voltage traces for 60 electrodes and includes functions for activation-time determination, the production of activation-time heat maps with activation time and isoline display. Furthermore, local conduction velocities are semi-automatically calculated along with their corresponding vector plots. MultiElec allows ad hoc signal suppression, enabling the user to easily and efficiently handle signal artefacts and for incomplete data sets to be analysed. Voltage traces and heat maps can be simply exported for figure production and presentation. In addition, our platform is able to produce 3D videos of signal progression over all 60 electrodes. Functions are controlled entirely by a single GUI with no need for command line input or any understanding of MATLAB code. MultiElec is open source under the terms of the GNU General Public License as published by the Free Software Foundation, version 3. Both the program and source code are available to download from http://www.cancer.manchester.ac.uk/MultiElec/.     

EMDA: A Python package for Electron Microscopy Data Analysis

An open-source Python library EMDA for cryo-EM map and model manipulation is presented with a specific focus on validation. The use of several functionalities in the library is presented through several examples. The utility of local correlation as a metric for identifying map-model differences and unmodeled regions in maps, and how it is used as a metric of map-model validation is demonstrated. The mapping of local correlation to individual atoms, and its use to draw insights on local signal variations are discussed. EMDA’s likelihood-based map overlay is demonstrated by carrying out a superposition of two domains in two related structures. The overlay is carried out first to bring both maps into the same coordinate frame and then to estimate the relative movement of domains. Finally, the map magnification refinement in EMDA is presented with an example to highlight the importance of adjusting the map magnification in structural comparison studies.